{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2468827930174564,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.7872959971427917,
      "learning_rate": 1.917206982543641e-05,
      "loss": 0.7834,
      "step": 500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 0.9406130313873291,
      "learning_rate": 1.834081463009144e-05,
      "loss": 0.4895,
      "step": 1000
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.4806763529777527,
      "learning_rate": 1.7509559434746467e-05,
      "loss": 0.4473,
      "step": 1500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 0.5443118214607239,
      "learning_rate": 1.6678304239401496e-05,
      "loss": 0.4326,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.33564111590385437,
      "eval_runtime": 26.4357,
      "eval_samples_per_second": 18.687,
      "eval_steps_per_second": 4.691,
      "step": 2406
    },
    {
      "epoch": 1.0390689941812137,
      "grad_norm": 0.7427258491516113,
      "learning_rate": 1.5847049044056525e-05,
      "loss": 0.4225,
      "step": 2500
    },
    {
      "epoch": 1.2468827930174564,
      "grad_norm": 0.4491533637046814,
      "learning_rate": 1.5015793848711555e-05,
      "loss": 0.3857,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 12030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7306885728829440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}